Skip to main content
  1. Sign up — Create an account at platform.respan.ai
  2. Create an API key — Generate one on the API keys page
  3. Add credits or a provider key — Add credits on the Credits page or connect your own provider key on the Integrations page
Add the Docs MCP to your AI coding tool to get help building with Respan. No API key needed.
{
  "mcpServers": {
    "respan-docs": {
      "url": "https://docs.respan.ai/mcp"
    }
  }
}

​
What is Aleph Alpha?

Aleph Alpha is a European AI company providing sovereign AI solutions. The Aleph Alpha Python client supports completions, embeddings, and semantic search. Respan can auto-instrument all Aleph Alpha calls for tracing and observability.
Aleph Alpha uses a proprietary API format, so only Tracing setup is available. Gateway routing is not supported.

​
Setup

1

Install packages

pip install respan-ai opentelemetry-instrumentation-alephalpha aleph-alpha-client python-dotenv
2

Set environment variables

export ALEPH_ALPHA_API_KEY="YOUR_ALEPH_ALPHA_API_KEY"
export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"
3

Initialize and run

import os
from dotenv import load_dotenv

load_dotenv()

from aleph_alpha_client import Client, CompletionRequest, Prompt
from respan import Respan

# Auto-discover and activate all installed instrumentors (Traceloop)
respan = Respan(is_auto_instrument=True)

# Initialize Aleph Alpha client
client = Client(token=os.getenv("ALEPH_ALPHA_API_KEY"))

# Calls go directly to Aleph Alpha, auto-traced by Respan
request = CompletionRequest(
    prompt=Prompt.from_text("Say hello in three languages."),
    maximum_tokens=128,
)
response = client.complete(request, model="luminous-supreme-control")
print(response.completions[0].completion)
respan.flush()
4

View your trace

Open the Traces page to see your auto-instrumented LLM spans.

​
Configuration

ParameterTypeDefaultDescription
api_keystr | NoneNoneFalls back to RESPAN_API_KEY env var.
base_urlstr | NoneNoneFalls back to RESPAN_BASE_URL env var.
is_auto_instrumentbool | NoneFalseAuto-discover and activate all installed instrumentors via OpenTelemetry entry points.
customer_identifierstr | NoneNoneDefault customer identifier for all spans.
metadatadict | NoneNoneDefault metadata attached to all spans.
environmentstr | NoneNoneEnvironment tag (e.g. "production").

​
Attributes

Attach customer identifiers, thread IDs, and metadata to spans.

​
In Respan()

Set defaults at initialization — these apply to all spans. 
from respan import Respan

respan = Respan(
    is_auto_instrument=True,
    customer_identifier="user_123",
    metadata={"service": "completion-api", "version": "1.0.0"},
)

​
With propagate_attributes

Override per-request using a context manager. 
from aleph_alpha_client import Client, CompletionRequest, Prompt
from respan import Respan, workflow, propagate_attributes

respan = Respan(
    is_auto_instrument=True,
    metadata={"service": "completion-api", "version": "1.0.0"},
)
client = Client(token=os.getenv("ALEPH_ALPHA_API_KEY"))

@workflow(name="handle_request")
def handle_request(user_id: str, question: str):
    with propagate_attributes(
        customer_identifier=user_id,
        thread_identifier="conv_001",
        metadata={"plan": "enterprise"},
    ):
        request = CompletionRequest(
            prompt=Prompt.from_text(question),
            maximum_tokens=128,
        )
        response = client.complete(request, model="luminous-supreme-control")
        print(response.completions[0].completion)
AttributeTypeDescription
customer_identifierstrIdentifies the end user in Respan analytics.
thread_identifierstrGroups related messages into a conversation.
metadatadictCustom key-value pairs. Merged with default metadata.

​
Decorators

Use @workflow and @task to create structured trace hierarchies. 
from aleph_alpha_client import Client, CompletionRequest, Prompt
from respan import Respan, workflow, task

respan = Respan(is_auto_instrument=True)
client = Client(token=os.getenv("ALEPH_ALPHA_API_KEY"))

@task(name="generate_outline")
def outline(topic: str) -> str:
    request = CompletionRequest(
        prompt=Prompt.from_text(f"Create a brief outline about: {topic}"),
        maximum_tokens=256,
    )
    response = client.complete(request, model="luminous-supreme-control")
    return response.completions[0].completion

@workflow(name="content_pipeline")
def pipeline(topic: str):
    plan = outline(topic)
    request = CompletionRequest(
        prompt=Prompt.from_text(f"Write content from this outline: {plan}"),
        maximum_tokens=512,
    )
    response = client.complete(request, model="luminous-supreme-control")
    print(response.completions[0].completion)

pipeline("Benefits of API gateways")
respan.flush()

​
Examples

​
Basic completion

request = CompletionRequest(
    prompt=Prompt.from_text("Say hello in three languages."),
    maximum_tokens=128,
)
response = client.complete(request, model="luminous-supreme-control")
print(response.completions[0].completion)